© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 5692
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and personal health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >({
    -0.49
    karta
    -0.47
     kaarangay
    -0.46
    /**
    -0.46
     local
    -0.42
    اسة
    -0.41
    chenken
    -0.40
    ><?
    -0.40
     nhấn
    -0.40
     mor
    -0.40
    POSITIVE LOGITS
    ut
    1.76
    UT
    1.40
    uts
    1.20
     ut
    1.15
    UTS
    1.09
    utan
    1.00
    utf
    0.99
     UT
    0.99
    utat
    0.96
    utin
    0.95
    Activations Density 2.306%

    No Known Activations